{"id":"W4411233190","doi":"10.1109/sustech63138.2025.11025610","title":"Federated Learning for Anomaly Detection in Energy Consumption Data: Assessing the Vulnerability to Adversarial Attacks","year":2025,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Adversarial system; Vulnerability (computing); Computer science; Anomaly detection; Energy consumption; Computer security; Consumption (sociology); Artificial intelligence; Energy (signal processing); Data mining; Machine learning; Statistics; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001887206,0.0001632865,0.0001997639,0.0001938733,0.0007629467,0.0006228525,0.0009264375,0.0001098003,0.00001242048],"category_scores_gemma":[0.001634868,0.0001340255,0.00004175916,0.0007512498,0.00004334902,0.001155083,0.0008670895,0.0003857327,0.000004635037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002017204,"about_ca_system_score_gemma":0.000155176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007110571,"about_ca_topic_score_gemma":0.001025226,"domain_scores_codex":[0.997835,0.0005622475,0.0003602406,0.0007317389,0.0001889871,0.000321781],"domain_scores_gemma":[0.9980652,0.001073155,0.0001075853,0.0005946358,0.0001151572,0.00004429649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000967698,0.0000658298,0.02089413,0.00003606089,0.00003886069,0.000003225052,0.0002398,0.4408378,0.004035922,0.01033915,0.0002914301,0.523121],"study_design_scores_gemma":[0.0006347861,0.00003691284,0.01860027,0.00002633775,0.0000100284,0.000001790773,0.00009037896,0.9728283,0.001564763,0.0004585088,0.005595233,0.0001526698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04164607,0.00002039374,0.9545783,0.001403688,0.001052288,0.0003070555,7.136405e-7,0.0002133144,0.0007782122],"genre_scores_gemma":[0.975198,0.000002302026,0.02383669,0.0004441873,0.0001153817,0.00004968604,0.00001593474,0.000008997466,0.0003288092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335519,"threshold_uncertainty_score":0.6006181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03915970466099027,"score_gpt":0.3618185106294455,"score_spread":0.3226588059684552,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}